US 12,406,197 B2
Prediction and metrology of stochastic photoresist thickness defects
Anatoly Burov, Austin, TX (US); Guy Parsey, Ann Arbor, MI (US); Kunlun Bai, Campbell, CA (US); Pradeep Vukkadala, Santa Clara, CA (US); Cao Zhang, Ann Arbor, MI (US); John S. Graves, Austin, TX (US); Xiaohan Li, Ann Arbor, MI (US); and Craig Higgins, Cedar Park, TX (US)
Assigned to KLA Corporation, Milpitas, CA (US)
Filed by KLA Corporation, Milpitas, CA (US)
Filed on Jun. 2, 2021, as Appl. No. 17/337,373.
Claims priority of provisional application 63/106,356, filed on Oct. 28, 2020.
Prior Publication US 2022/0129775 A1, Apr. 28, 2022
Int. Cl. G03F 7/00 (2006.01); G03F 1/70 (2012.01); G06N 7/01 (2023.01); G06N 20/00 (2019.01)
CPC G06N 7/01 (2023.01) [G03F 1/70 (2013.01); G06N 20/00 (2019.01)] 19 Claims
OG exemplary drawing
 
1. A method comprising:
inputting a mask pattern for a semiconductor device into a machine learning module, wherein the mask pattern is a design file that includes a polygon shape of a mask; and
determining a photoresist thickness probability distribution for the semiconductor device based on the mask pattern using the machine learning module, wherein the machine learning module includes a first model, a second model, and a third model, wherein the first model predicts a mask diffraction pattern given a rasterized mask image, wherein the second model predicts an image in photoresist given the mask diffraction pattern, and wherein the third model predicts photoresist thickness distribution given the image in photoresist.